Style Transfer via Zero-Shot Monolingual Neural Machine Translation
Text style transfer is the task of altering stylistic features of a text while preserving its meaning and fluency. It can be viewed as a sequence-to-sequence transformation task, but the scarcity of directly annotated parallel data makes it unfeasible for most settings. We propose an approach to style transfer that builds on the idea of zero-shot machine translation. It performs style transfer within a neural machine translation model, without requiring any parallel style-adapted texts, relying instead only on regular language-parallel data. The method is applicable to multiple languages within a single model. We outline the method, describe our experiments with it, and, finally, present a thorough automatic and manual evaluation of the approach in comparison to a baseline and independently, showing that our zero-shot model outperforms the supervised baseline on several aspects according to human judgments, and is reliable for a number of style transfer aspects, while not depending on annotated data.
Graduation Thesis language
Graduation Thesis type
Master - Computer Science